Text Generation
Transformers
Safetensors
mistral
Merge
mergekit
lazymergekit
text-generation-inference
Instructions to use Ppoyaa/LexiLumin-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ppoyaa/LexiLumin-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ppoyaa/LexiLumin-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ppoyaa/LexiLumin-7B") model = AutoModelForCausalLM.from_pretrained("Ppoyaa/LexiLumin-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ppoyaa/LexiLumin-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ppoyaa/LexiLumin-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ppoyaa/LexiLumin-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ppoyaa/LexiLumin-7B
- SGLang
How to use Ppoyaa/LexiLumin-7B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Ppoyaa/LexiLumin-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ppoyaa/LexiLumin-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Ppoyaa/LexiLumin-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ppoyaa/LexiLumin-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Ppoyaa/LexiLumin-7B with Docker Model Runner:
docker model run hf.co/Ppoyaa/LexiLumin-7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,21 +8,9 @@ license: apache-2.0
|
|
| 8 |
|
| 9 |
# LexiLumin-7B
|
| 10 |
|
| 11 |
-
LexiLumin-7B is a merge of
|
| 12 |
This model excels in roleplaying and storytelling.
|
| 13 |
|
| 14 |
-
## 🧩 Configuration
|
| 15 |
-
|
| 16 |
-
```yaml
|
| 17 |
-
models:
|
| 18 |
-
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
|
| 19 |
-
- model: CultriX/MonaTrix-v4-7B-DPO
|
| 20 |
-
- model: S-miguel/The-Trinity-Coder-7B
|
| 21 |
-
- model: mlabonne/AlphaMonarch-7B
|
| 22 |
-
merge_method: model_stock
|
| 23 |
-
base_model: CultriX/MonaTrix-v4-7B-DPO
|
| 24 |
-
dtype: bfloat16
|
| 25 |
-
```
|
| 26 |
# 🏆 Open LLM Leaderboard Evaluation Results
|
| 27 |
| Metric |Value|
|
| 28 |
|---------------------------------|----:|
|
|
|
|
| 8 |
|
| 9 |
# LexiLumin-7B
|
| 10 |
|
| 11 |
+
LexiLumin-7B is a merge of four models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing).
|
| 12 |
This model excels in roleplaying and storytelling.
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
# 🏆 Open LLM Leaderboard Evaluation Results
|
| 15 |
| Metric |Value|
|
| 16 |
|---------------------------------|----:|
|